CICERO
It won Diplomacy by out-talking humans — and no one called it out
Latest: Science publication + code release (November 2022)
The first AI to achieve human-level play in Diplomacy — a game requiring natural-language negotiation, persuasion and cooperation with people. CICERO combined a dialogue language model with a strategic planning engine that inferred other players' intentions. Published in Science (November 2022); code and models were open-sourced for research.
Why it matters
The first AI to reach human-level play in Diplomacy, a game won through natural-language negotiation and cooperation. A 2.7B-parameter dialogue model fine-tuned on 40,000+ webDiplomacy games, coupled with a strategic planner, scored more than double the human average and ranked in the top 10% of players. Code and weights are open.
Facts
- An AI that won a game of lying and alliances not by out-calculating humans, but by out-talking them.
- Across 40 anonymous online games against 82 humans, CICERO scored more than double the average of its opponents and ranked in the top 10% of repeat players — sending about 130 negotiation messages per game without being unmasked as an AI.
- Played 40 webDiplomacy.net blitz games between Aug 19 and Oct 13, 2022, negotiating with humans in free-form English — and players didn't flag it as an AI during league play.
Try it yourself
Code and model weights on GitHub ↗ Official CICERO research page ↗ Meta AI blog post ↗
Lineage
Sources
Science ↗GitHub · diplomacy_cicero ↗Meta AI research ↗